Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15909
    Prev
    Next
    INDEX
    Explanations

    references to brushes and related tools or techniques in cooking and makeup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    'brush' or 'brushes'

    np_acts-logits-general · gemini-2.0-flash

    brush and toothbrush

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enterOuterAlt
    -0.42
    лтемелер
    -0.41
    لينكات
    -0.41
    CloseOperation
    -0.41
    hoeddwyd
    -0.40
    ViewImports
    -0.38
     Caw
    -0.38
    
    -0.37
     Wyd
    -0.37
    хождение
    -0.37
    POSITIVE LOGITS
     brush
    1.45
     brushes
    1.37
     Brush
    1.30
     Brushes
    1.18
    Brush
    1.14
    brush
    1.13
    brushes
    1.10
     brushing
    0.97
     brosse
    0.96
     bristles
    0.95
    Activations Density 0.098%

    No Known Activations